CN 119810518 A

摘要

本发明公开了一种基于神经影像结合机器学习识别帕金森病的稳定亚型的方法，具体识别方法是基于PD个体的结构异质性，采用判别分析的半监督机器学习方法来识别首诊未识别服药PD个体的神经解剖亚型，判别分析方法主要同时进行分类和聚类，其由线性最大间隔分类器形成的多面体将PD个体和健康个体区分开，再根据患者与多面体不同超平面的距离将PD个体进行聚类，该方法对于受到与疾病无关的个体差异的影响较小，有助于识别真正的疾病亚型；本发明基于PD亚型患者的黑质自由水值作为神经炎症和多巴胺系统损伤为判断指标，监测疾病的进程；同时为了提高临床决策质量及个体治疗效果。

英文（機器翻譯）： The present invention discloses a method for identifying stable subtypes of Parkinson's disease based on neuroimaging combined with machine learning. The specific identification method is based on the structural heterogeneity of PD individuals, and a semi-supervised machine learning method of discriminant analysis is used to identify the neuroanatomical subtypes of PD individuals who are not identified as taking medication at the first visit. The discriminant analysis method mainly performs classification and clustering at the same time.…

這裡只列摘要開頭，完整內容在 PDF 裡。